Glue job

		import sys

		import boto3

		from awsglue.transforms import *

		from awsglue.utils import getResolvedOptions

		from pyspark.context import SparkContext

		from awsglue.context import GlueContext

		from awsglue.job import Job



		## @params: [JOB_NAME]

		args = getResolvedOptions(sys.argv, ['JOB_NAME'])



		sc = SparkContext()

		glueContext = GlueContext(sc)

		spark = glueContext.spark_session

		job = Job(glueContext)

		job.init(args['JOB_NAME'], args)



		client = boto3.client('glue',region_name='ap-southeast-2')



		databaseName = 'tpc-ds-csv'

		print '\ndatabaseName: ' + databaseName



		Tables = client.get_tables( DatabaseName = databaseName )

		tableList = Tables ['TableList']



		for table in tableList:

		   tableName = table['Name']

		   print '\n-- tableName: '+tableName

		   datasource0 = glueContext.create_dynamic_frame.from_catalog(database = "tpc-ds-csv",
                       table_name = tableName, transformation_ctx = "datasource0")

		   datasink4 = glueContext.write_dynamic_frame.from_options(frame = datasource0, connection_type = "s3", 
                       connection_options = {"path": "s3://aws-glue-tpcds-parquet/"+ tableName + "/"},
                       format = "parquet", transformation_ctx = "datasink4")

		job.commit()